1
DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution
无需额外训练，扩散模型直接优化视频超分辨率，刷新生成质量与效率。
arXiv:2605.30431v1 Announce Type: new Abstract: Recent progress in video diffusion models has enabled remarkable generative fidelity, yet leveraging t…